臺灣博碩士論文加值系統

乳癌是近年來已全球化的婦女死亡的主要原因。如果可以及早查出腫瘤的存在，乳癌治癒的機會將大增不少，所以美國癌症協會建議二十歲以上的女性每年要做乳房檢查。在臨床上，電腦輔助分析系統可以幫助放射師分辨惡性和良性的乳房腫瘤。如果電腦輔助系統可以提供更高的準確率，便可以大幅減少乳房切片檢查的需求。在本論文，乳房彩色彈性影像（color elasticity image）為輸入檔，圖中藍色區域是比較硬的組織，綠色到紅色區域是比較軟的組織。我們提出對乳房彈性影像根據幾個特徵來做腫瘤的分析。惡性和良性的腫瘤具有不同的彈性特質，一般情況，惡性腫瘤比較硬，良性腫瘤比較軟，所以我們利用此特徵來分析。實驗用的影像，是先由醫生把腫瘤的輪廓先畫出來後，我們再用所提出的方法分析腫瘤的良惡性。除了使用彈性特徵來分析腫瘤，我們還用BI-RADS訂出的標準來分析腫瘤。在實驗中，我們利用181個病理學驗證的病例來測試所提出之電腦輔助系統的準確率，其中包含113個良性與68個惡性。在乳房彈性影像中，所提出的方法針對彈性特徵，準確率為86.19%，使用B-mode特徵，準確率為82.32%，彈性特徵和B-mode特徵同時分析的話，準確率為90.61%。

In recent years, the breast cancer is globally the main causes of death for women. If a cancer can be found out earlier, the curability of the breast cancer will increase greatly; therefore American Cancer Society suggests that women more than twenty years old should take breast examination annually. Clinically, the computer-aided analysis can help radiologists to differentiate the benign and malignant tumors. If computer-aided analysis provides higher accuracy, the demand of the breast biopsy can be reduced. In this paper, the color elastographic breast images are used to diagnose the breast tumors, on which the blue region represents the harder tissues, while the green to red region represents the softer tissues. We propose an analysis method using several features for differentiating tumor malignancy of breast elastography. The malignant and benign tumors have different elasticity characteristic. Generally, the malignant tumor is harder, while the benign tumor is softer, so we make use of this characteristic to apply in our analysis method. The tumor contours of the input images in our experiment were drawn by physician in advance, and then we applied our analysis method to the images to classify the malignancy of them. Other than elastographic features, we also applied BI-RADS standard features to analyze the malignancy of the tumor. In our experiments, 181 pathology-proven cases are used to test the accuracy of our proposed computer aided system; among them, there includes 113 benign and 68 malignant breast tumors. The accuracy rate of proposed computer aided analysis method towards elastography features can achieve 86.19% on breast elastography, on B-mode features can achieve 82.32%, and on both features can achieve 90.61%.

摘 要 i
ABSTRACT ii
ACKNOWLEDGEMENTS iii
TABLE OF CONTENTS iv
LIST OF FIGURES v
LIST OF TABLES ix

Chapter 1 Introduction 1
Chapter 2 Related Works 4
2.1 Color Breast Elastography 4
2.2 ACR BI-RADS B-mode US Features 7
2.3 HSV Color Space 10
Chapter 3 Tumor Analysis Using Color Breast Elastography 12
3.1 Elastographic Features 13
3.1.1 Difference between Inner and Outer Bands 13
3.1.2 Ratio between Inner and Outer Bands 15
3.1.3 Mean 15
3.1.4 The Most Frequent Hue (Mode) 16
3.1.5 Median 17
3.2 ACR BI-RADS B-mode US Features 17
3.2.1 Orientation 17
3.2.2 Margin Undulation 19
3.2.3 Margin Angular 20
3.2.4 Average Gradient Magnitude within Boundary Bands 21
3.2.5 Variance 23
3.2.6 Variance of Gradient Magnitude of the Tumor 23
Chapter 4 Results and Discussion 25
4.1 Elastographic and B-mode Features 26
4.2 Neural Network using Elastographic and B-mode Features 26
Chapter 5 Conclusion and Future Works 38
REFERENCES 40

[1]American Cancer Society, "Cancer Facts and Figures 2007," 2007.
[2]R. Chandrasekhar, J. Ophir, T. Krouskop, and K. Ophir, "Elastographic image quality vs. tissue motion in vivo," Ultrasound in Medicine and Biology, vol. 32, pp. 847-855, Jun 2006.
[3]B. S. Garra, E. I. Cespedes, J. Ophir, S. R. Spratt, R. A. Zuurbier, C. M. Magnant, and M. F. Pennanen, "Elastography of breast lesions: Initial clinical results," Radiology, vol. 202, pp. 79-86, Jan 1997.
[4]K. Hoyt, F. Forsberg, and J. Ophir, "Analysis of a hybrid spectral strain estimation technique in elastography," Physics in Medicine and Biology, vol. 51, pp. 197-209, Jan 21 2006.
[5]J. Ophir, I. Cespedes, H. Ponnekanti, Y. Yazdi, and X. Li, "Elastography - a Quantitative Method for Imaging the Elasticity of Biological Tissues," Ultrasonic Imaging, vol. 13, pp. 111-134, Apr 1991.
[6]A. Itoh, E. Ueno, E. Tohno, H. Kamma, H. Takahashi, T. Shiina, M. Yamakawa, and T. Matsumura, "Breast disease: Clinical application of US elastography for diagnosis," Radiology, vol. 239, pp. 341-350, May 2006.
[7]C. Balleyguier, S. Ayadi, K. Van Nguyen, D. Vanel, C. Dromain, and R. Sigal, "BIRADS (TM) classification in mammography," European Journal of Radiology, vol. 61, pp. 192-194, Feb 2007.
[8]A. A. Tardivon, A. Athanasiou, F. Thibault, and C. El Khoury, "Breast imaging and reporting data system (BIRADS): Magnetic resonance imaging," European Journal of Radiology, vol. 61, pp. 212-215, Feb 2007.
[9]A. Thomas, S. Kummel, F. Fritzsche, M. Warm, B. Ebert, B. Hamm, and T. Fischer, "Real-time sonoelastography performed in addition to B-mode ultrasound and mammography: Improved differentiation of breast lesions?," Academic Radiology, vol. 13, pp. 1496-1504, Dec 2006.
[10]G. Rizzatto, R. Chersevani, and M. Locatelli, "The Contribution of New US Technologies to US Differential Diagnosis of Nonpalpable Lesions," Radiol Oncol, vol. 38(Suppl 1), p. S139, November 24, 2004 2004.
[11]A. S. Hong, E. L. Rosen, M. S. Soo, and J. A. Baker, "BI-RADS for sonography: Positive and negative predictive values of sonographic features," American Journal of Roentgenology, vol. 184, pp. 1260-1265, Apr 2005.
[12]G. Rahbar, A. C. Sie, G. C. Hansen, J. S. Prince, M. L. Melany, H. E. Reynolds, V. P. Jackson, J. W. Sayre, and L. W. Bassett, "Benign versus malignant solid breast masses: US differentiation," Radiology, vol. 213, pp. 889-894, Dec 1999.
[13]T. Fischer, F. Diekmann, and A. Thomas, "Screening Programs : Are New Techniques Needed in Modern Sonography ?," Visions, vol. 8, p. 9, 2005.
[14]R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2/E, Second Edition ed. Upper Saddle River, New Jersey: Prentice Hall, 2002.
[15]L. G. Shapiro and G. C. Stockman, Computer Vision. Upper Saddle River, New Jersey: Prentice-Hall, Inc., 2001.
[16]K. Moodley and H. Murrell, "A colour-map plugin for the open source, Java based, image processing package, ImageJ," Computers & Geosciences, vol. 30, pp. 609-618, Jul 2004.
[17]D. Sage and M. Unser, "Easy Java programming for teaching image-processing," Thessaloniki, 2001, pp. 298-301.
[18]T. T. Soong, Fundamentals of Probability and Statistics for Engineers: Wiley-Interscience, 2004.
[19]A. K. Jain, "Fundamentals of Digital Image Processing," in Prentice Hall Information and System Sciences Series, T. Kailath, Ed. Englewood Cliffs, New Jersey: Prentice Hall, 1989.
[20]A. R. Feinstein, Principles of Medical Statistics. Florida, USA: Chapman & Hall/CRC September 14, 2001.
[21]J. Khan, J. S. Wei, M. Ringner, L. H. Saal, M. Ladanyi, F. Westermann, F. Berthold, M. Schwab, C. R. Antonescu, C. Peterson, and P. S. Meltzer, "Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks," Nature Medicine, vol. 7, pp. 673-679, Jun 2001.
[22]P. M. Ravdin, G. M. Clark, S. G. Hilsenbeck, M. A. Owens, P. Vendely, M. R. Pandian, and W. L. Mcguire, "A Demonstration That Breast-Cancer Recurrence Can Be Predicted by Neural Network Analysis," Breast Cancer Research and Treatment, vol. 21, pp. 47-53, 1992.
[23]T.-S. Li, "Feature selection for classification by using a GA-based neural network approach," Journal of the Chinese Institute of Industrial Engineers, vol. 23, pp. 55-65, 2006.
[24]N. Harbeck, R. Kates, K. Ulm, H. Graeff, and M. Schmitt, "Neural network analysis of follow-up data in primary breast cancer," International Journal of Biological Markers, vol. 15, pp. 116-122, Jan-Mar 2000.
[25]P. M. Ravdin and G. M. Clark, "A Practical Application of Neural Network Analysis for Predicting Outcome of Individual Breast-Cancer Patients," Breast Cancer Research and Treatment, vol. 22, pp. 285-293, 1992.
[26]M. Stone, "Cross-Validatory Choice and Assessment of Statistical Predictions," Journal of the Royal Statistical Society Series B-Methodological, vol. 36, pp. 111-147, 1974.
[27]T. Matsumura, R. Shinomura, T. Mitake, H. Kanda, M. Yamakawa, and T. Shiina, "Estimation of pressure-distribution effects upon elasticity imaging," in Ultrasonics Symposium, 2005 IEEE, Rotterdam, Netherlands, 2005, pp. 1759-1762.
[28]H. Zhi, B. Ou, B. M. Luo, X. Feng, Y. L. Wen, and H. Y. Yang, "Comparison of ultrasound elastography, mammography, and sonography in the diagnosis of solid breast lesions," Journal of Ultrasound in Medicine, vol. 26, pp. 807-815, Jun 2007.